© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3483
    Prev
    Next
    INDEX
    Explanations

    "is a" phrases and concepts that are being defined

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating concepts or definitions

    np_token-act-pair-logits · gpt-4o-mini

    a/an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     culturelles
    -0.43
     clínicas
    -0.42
    Its
    -0.42
     voici
    -0.41
     dependencia
    -0.40
     السابق
    -0.40
     tomadas
    -0.40
     оно
    -0.40
     efficacité
    -0.40
     venons
    -0.40
    POSITIVE LOGITS
     lenker
    0.74
    }")]
    0.74
    Datuak
    0.69
     autorytatywna
    0.69
     Signalez
    0.67
    ]")]
    0.67
    Rujuakan
    0.66
    Референце
    0.65
     way
    0.63
     core
    0.63
    Activations Density 1.394%

    No Known Activations